Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    playoff contention, performance, results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.85
     페
    0.79
    ラ
    0.74
    페
    0.74
    ل
    0.68
    로
    0.68
    List
    0.67
     C
    0.66
    ような
    0.66
     chaired
    0.66
    POSITIVE LOGITS
    ти
    0.76
     exhibits
    0.73
    та
    0.70
     playoffs
    0.70
     здания
    0.69
    ',$
    0.68
    appers
    0.66
     equips
    0.66
     árboles
    0.66
     emphasises
    0.66
    Act Density 0.002%

    No Known Activations